© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4431
    Prev
    Next
    INDEX
    Explanations

    instances of the word "draw" and its variants, indicating a focus on drawing or related actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inoxydable
    -0.89
    Collegamenti
    -0.85
    ptonshire
    -0.84
    EndInit
    -0.82
    EndGlobalSection
    -0.82
    XmlAccessorType
    -0.81
    /**
    -0.80
     @"/
    -0.79
     onPostExecute
    -0.78
     AssemblyCulture
    -0.77
    POSITIVE LOGITS
     drawn
    1.67
     draw
    1.48
     Draws
    1.48
     Drawn
    1.47
     DRAW
    1.45
     draws
    1.45
     Draw
    1.44
    Draw
    1.42
    draw
    1.40
    drawn
    1.40
    Activations Density 0.109%

    No Known Activations